library(dplyr)
library(readr)
histologies_df <- read_tsv("../../data/pbta-histologies.tsv")
Parsed with column specification:
cols(
.default = col_character(),
OS_days = [32mcol_double()[39m,
age_last_update_days = [32mcol_double()[39m,
normal_fraction = [32mcol_double()[39m,
tumor_fraction = [32mcol_double()[39m,
tumor_ploidy = [32mcol_double()[39m
)
See spec(...) for full column specifications.
chordoma_samples <- histologies_df %>%
filter(short_histology=="Chordoma") %>%
pull(Kids_First_Biospecimen_ID)
focal_cn_df <- read_tsv("../focal-cn-file-preparation/results/controlfreec_annotated_cn_autosomes.tsv.gz")
Parsed with column specification:
cols(
biospecimen_id = [31mcol_character()[39m,
status = [31mcol_character()[39m,
copy_number = [32mcol_double()[39m,
ploidy = [32mcol_double()[39m,
ensembl = [31mcol_character()[39m,
gene_symbol = [31mcol_character()[39m,
cytoband = [31mcol_character()[39m
)
chordoma_loss <- focal_cn_df %>%
filter(biospecimen_id %in% chordoma_samples, gene_symbol=="SMARCB1")
chordoma_loss
#we need to include the sample_id field from pbta-histologies.tsv in the final table (field will allow #us to map between RNA-seq (e.g., SMARCB1 expression values) and WGS data (e.g., SMARCB1 focal copy #number status) from the same event for a given individual).
#To get the SMARCB1 jitter plot in the photo here #250 (comment), you will first need to read in the #collapsed expression data
expression_data <- read_rds(file.path("..", "..", "data", "pbta-gene-expression-rsem-fpkm-collapsed.stranded.rds"))
expression_data